TimeTraveler: Reinforcement Learning for Temporal Knowledge Graph Forecasting
Haohai Sun, Jialun Zhong, Yunpu Ma, Zhen Han, Kun He
2021Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing169 citationsDOIOpen Access PDF
Abstract
Temporal knowledge graph (TKG) reasoning is a crucial task that has gained increasing research interest in recent years. Most existing methods focus on reasoning at past timestamps to complete the missing facts, and there are only a few works of reasoning on known TKGs to forecast future facts. Compared with the completion task, the forecasting task is more difficult and faces two main challenges:
Topics & Concepts
TimestampComputer scienceReinforcement learningInferenceArtificial intelligenceMachine learningGraphBenchmark (surveying)Task (project management)Encoding (memory)Representation (politics)Theoretical computer scienceManagementLawGeodesyPoliticsEconomicsPolitical scienceGeographyComputer securityAdvanced Graph Neural NetworksTopic ModelingBioinformatics and Genomic Networks